Papers Visual Prompt Tuning
“Visual Prompt Tuning” 태그가 달린 논문 88편 · 필터 해제
When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuning
Foundation models for medical image segmentation, like prompt-based MedSAM, generalize well across domains and modalities, often in zero or few-shot setups. However, their performance depends on the quality of prompts an…
Medical Image SegmentationVisual Prompt TuningDINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing
With the increasing diversity of spoofing attacks, there is a growing demand for unified Face Anti-Spoofing (FAS) models capable of detecting both physical and digital threats. While existing Vision-Language Models (VLMs…
Visual Prompt TuningFace Anti-SpoofingFedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning
With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates…
Knowledge DistillationVisual Prompt TuningFederated LearningHow many labels do you need? A decision framework for cross-habitat marine species recognition
Automated image recognition is increasingly used to scale ecological monitoring beyond manual annotation, yet ecologists lack evidence-based guidance on how much labelling effort reliable deployment at new sites requires…
Visual Prompt TuningLayer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
Visual prompt tuning has emerged as a parameter-efficient fine-tuning approach for adapting large-scale Vision Transformers (ViTs) to downstream tasks. As its learnable prompts are applied in input and feature spaces, pr…
parameter-efficient fine-tuningVisual Prompt TuningSparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonly leverage transferable representations …
Visual Prompt TuningSpike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization
Pre-trained vision models have found widespread application across diverse domains. Prompt tuning-based methods have emerged as a parameter-efficient paradigm for adapting pre-trained vision models. While effective on st…
Visual Prompt TuningVisual Prompt-Agnostic Evolution
Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT …
Visual Prompt TuningTest-Time Adaptive Object Detection with Foundation Model
In recent years, test-time adaptive object detection has attracted increasing attention due to its unique advantages in online domain adaptation, which aligns more closely with real-world application scenarios. However, …
Test-time AdaptationVisual Prompt TuningDomain AdaptationObject DetectionPrompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers
Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its paramet…
parameter-efficient fine-tuningVisual Prompt TuningFederated LearningVIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
In the era of large-scale foundation models, fully fine-tuning pretrained networks for each downstream task is often prohibitively resource-intensive. Prompt tuning offers a lightweight alternative by introducing tunable…
Visual Prompt TuningPrompt-based Adaptation in Large-scale Vision Models: A Survey
In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the "pretrain-the…
Test-time AdaptationVisual Prompt TuningPoint CloudsHuman3R: Everyone Everywhere All at Once
We present Human3R, a unified, feed-forward framework for online 4D human-scene reconstruction, in the world frame, from casually captured monocular videos. Unlike previous approaches that rely on multi-stage pipelines, …
Camera Pose EstimationVisual Prompt TuningHuman Mesh RecoveryDepth EstimationRobust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain inf…
Visual Prompt TuningRgb-T TrackingAdaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge
Atypical mitotic figures (AMFs) are clinically relevant indicators of abnormal cell division, yet their reliable detection remains challenging due to morphological ambiguity and scanner variability. In this work, we inve…
Visual Prompt TuningTowards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (…
Personalized Federated LearningVisual Prompt TuningA Foundation Model for DAS Signal Recognition and Visual Prompt Tuning of the Pre-trained Model for Downstream Tasks
Distributed Acoustic Sensing (DAS) technology finds growing applications across various domains. However, data distribution disparities due to heterogeneous sensing environments pose challenges for data-driven artificial…
Domain GeneralizationVisual Prompt TuningGait RecognitionVisual Instance-aware Prompt Tuning
Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. …
parameter-efficient fine-tuningVisual Prompt TuningPrompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization
Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains. Notably, recent advances in pre-trained Visual Foundation Models (VFMs), such as CLIP, have demons…
DescriptiveDisentanglementDomain GeneralizationLarge Language Model+1Attention to Burstiness: Low-Rank Bilinear Prompt Tuning
Visual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts. In VPT, we uncover …
Visual Prompt Tuning